PaperHub
影响力指数
91.83/100
前 0.4%
全站排名 #286
发表论文42 篇
平均评分5.6
年均产出14.0 篇/年

Kai-Wei Chang

Associate Professor@University of California, Los Angeles·美国·OpenReview
研究方向

Fairness and Robustness in NLP · information extraction · Structured predictions · Natural Language Processing

6.5
13

OpenThoughts: Data Recipes for Reasoning Models

ICLR 2026Oral
5.0
35

ContextNav: Towards Agentic Multimodal In-Context Learning

ICLR 2026Poster
三作
5.0
20

VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation

ICLR 2026Poster
通讯
4.8
27

Learning to Rank Chain-of-Thought: Using a Small Model

ICLR 2026Desk Rejected
4.5
15

FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

ICLR 2026Rejected
4.5
12

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks

ICLR 2026Withdrawn
4.5
15

DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation

ICLR 2026Rejected
4.5
21

GTD: Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models

ICLR 2026Withdrawn
4.0
23

FrameMind: Frame-Interleaved Chain-of-Thought for Video Reasoning via Reinforcement Learning

ICLR 2026Rejected
三作
4.0
14

Kaleidoscopic Teaming in Multi Agent Simulations

ICLR 2026Rejected
4.0
29

ProcessLID: Step-wise Internal Reward in LLM Reasoning via Local Intrinsic Dimension

ICLR 2026Rejected
通讯
3.3
4

Energy-Driven Steering: Reducing False Refusals in Large Language Models

ICLR 2026Withdrawn
3.0
6

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

ICLR 2026Rejected
通讯
2.5
5

Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs

ICLR 2026Withdrawn
三作
7.8
27

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

NeurIPS 2025Spotlight
7.5
24

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

ICLR 2025Spotlight
7.3
16

Agree to Disagree? A Meta-Evaluation of LLM Misgendering

COLM 2025Poster
6.8
22

LaViDa: A Large Diffusion Model for Vision-Language Understanding

NeurIPS 2025Spotlight
6.8
27

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

NeurIPS 2025Poster
通讯
6.7
23

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

COLM 2025Poster
6.6
14

Contrastive Visual Data Augmentation

ICML 2025Poster
6.4
16

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

NeurIPS 2025Poster
通讯
6.3
27

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

ICLR 2025Poster
6.3
17

Customize Multi-modal RAI Guardrails with Precedent-based predictions

COLM 2025Poster
通讯
6.3
26

VideoPhy: Evaluating Physical Commonsense for Video Generation

ICLR 2025Poster
6.0
30

Controllable Generation via Locally Constrained Resampling

ICLR 2025Poster
二作
6.0
28

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

COLM 2025Poster
6.0
23

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

ICLR 2025Spotlight
6.0
12

Contradiction Retrieval via Contrastive Learning with Sparsity

ICML 2025Poster
三作
5.8
29

Contradiction Retrieval Via Sparse-Aware Sentence Embedding

ICLR 2025Rejected
三作
5.6
25

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

ICLR 2025Poster
5.5
6

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

ICML 2025Poster
通讯
5.2
38

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

ICLR 2025Poster
4.8
25

Q* Agent: Optimizing Language Agents with Q-Guided Exploration

ICLR 2025Rejected
通讯
-1

Unlearning as Multi-Task Optimization: a normalized gradient difference approach with adaptive learning rate

ICLR 2025Withdrawn
合作者 (20)